Data Preprocessing and Feature Engineering

Handle missing values using simple imputation strategies (mean, median, mode).

Encode categorical variables using one-hot encoding and label encoding, explaining the trade-offs.

Apply feature scaling techniques (standardization and normalization) and explain when each is appropriate.

Apply common strategies for handling outliers identified during EDA (e.g., clipping, removal).

Engineer new features from existing ones, including polynomial, interaction, and temporal features.

Build a reusable preprocessing pipeline using scikit-learn's Pipeline and ColumnTransformer.